Repositories list

• sae-trait-annotation

  Public
  [ICLR'26] Automatic Image-Level Morphological Trait Annotation for Organismal Images

  Python

  •

  MIT License

  •00 forks•44 stars•00 issues•00 pull requests•Updated May 18, 2026May 18, 2026

• Mind2Web-2

  Public
  [NeurIPS'25 D&B] Mind2Web-2 Benchmark: Evaluating Agentic Search with Agent-as-a-Judge

  benchmarkdatasetagents+ 2

  benchmarkdatasetagentscuawebagent

  Python

  •

  MIT License

  •66 forks•111111 stars•11 issue•00 pull requests•Updated May 17, 2026May 17, 2026

• QUEST

  Public
  Python

  •00 forks•88 stars•00 issues•00 pull requests•Updated May 17, 2026May 17, 2026

• ACuRL

  Public
  An Autonomous Curriculum Reinforcement Learning framework that steers agents to continually learn in specific environments with zero human data.

  Python

  •22 forks•3333 stars•11 issue•00 pull requests•Updated May 13, 2026May 13, 2026

• GUI-Agents-Paper-List

  Public
  Awesome GUI Agent Paper List

  TypeScript

  •4141 forks•780780 stars•11 issue•00 pull requests•Updated May 12, 2026May 12, 2026

• saev

  Public
  Sparse autoencoders for vision

  Python

  •

  MIT License

  •99 forks•6161 stars•77 issues•66 pull requests•Updated May 12, 2026May 12, 2026

• FREA

  Public
  RxnVerif: A chemical reaction feasibility prediction dataset.

  Creative Commons Attribution 4.0 International

  •00 forks•11 star•00 issues•00 pull requests•Updated May 8, 2026May 8, 2026

• D3-Gym

  Public
  Official code and data for the paper "D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery"

  Python

  •

  MIT License

  •00 forks•55 stars•11 issue•00 pull requests•Updated May 5, 2026May 5, 2026

• ScienceAgentBench

  Public
  [ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

  bioinformaticsgeosciencecode-generation+ 6

  bioinformaticsgeosciencecode-generationchemoinformaticstask-automationcognitive-neuroscienceai4sciencelarge-language-modelslanguage-agent

  Python

  •

  MIT License

  •1919 forks•137137 stars•55 issues•00 pull requests•Updated Apr 29, 2026Apr 29, 2026

• Loop-Think-Generalize

  Public
  Python

  •1313 forks•7878 stars•00 issues•00 pull requests•Updated Apr 9, 2026Apr 9, 2026

• LLM-IOAA

  Public
  Code and data for the paper "Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)" (https://arx…

  astronomyastrophysicsioaa+ 2

  astronomyastrophysicsioaaai4sciencelarge-language-models

  TeX

  •

  MIT License

  •11 fork•1919 stars•00 issues•00 pull requests•Updated Mar 20, 2026Mar 20, 2026

• UGround

  Public
  [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents

  artificial-intelligenceweb-agentsgui-agents

  artificial-intelligenceweb-agentsgui-agents

  Python

  •

  MIT License

  •1818 forks•315315 stars•66 issues•00 pull requests•Updated Mar 11, 2026Mar 11, 2026

• Explorer

  Public
  [ACL'25 (Findings)] Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents

  machine-learningsynthetic-dataset-generationweb-agents+ 1

  machine-learningsynthetic-dataset-generationweb-agentsgui-agents

  Python

  •

  MIT License

  •11 fork•2929 stars•00 issues•00 pull requests•Updated Feb 17, 2026Feb 17, 2026

• AutoElicit

  Public
  When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents

  Python

  •

  Apache License 2.0

  •00 forks•77 stars•00 issues•00 pull requests•Updated Feb 10, 2026Feb 10, 2026

• Misaligned-Action-Detection

  Public
  [ICML 2026] When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents

  Python

  •11 fork•88 stars•11 issue•00 pull requests•Updated Feb 10, 2026Feb 10, 2026

• RedTeamCUA

  Public
  [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments

  Python

  •

  Apache License 2.0

  •1010 forks•5353 stars•00 issues•00 pull requests•Updated Feb 9, 2026Feb 9, 2026

• cobalt

  Public
  Code and data for the paper "Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation"

  reinforcement-learningcode-generationcoding-assistant+ 2

  reinforcement-learningcode-generationcoding-assistantlarge-language-modelscoding-agent

  Python

  •

  MIT License

  •00 forks•99 stars•11 issue•00 pull requests•Updated Feb 4, 2026Feb 4, 2026

• GUI-Drag

  Public
  Python

  •00 forks•33 stars•00 issues•00 pull requests•Updated Feb 1, 2026Feb 1, 2026

• Online-Mind2Web

  Public
  An Illusion of Progress? Assessing the Current State of Web Agents

  Python

  •

  MIT License

  •1212 forks•176176 stars•22 issues•11 pull request•Updated Jan 2, 2026Jan 2, 2026

• SciNav

  Public
  00 forks•00 stars•00 issues•00 pull requests•Updated Dec 21, 2025Dec 21, 2025

• TravelPlanner

  Public
  [ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"

  planningautonomous-agentslarge-language-models+ 1

  planningautonomous-agentslarge-language-modelslanguage-agent

  Python

  •

  MIT License

  •7575 forks•513513 stars•00 issues•44 pull requests•Updated Nov 7, 2025Nov 7, 2025

• Mind2Web

  Public
  [NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist web agents

  Jupyter Notebook

  •

  MIT License

  •124124 forks•991991 stars•77 issues•44 pull requests•Updated Nov 5, 2025Nov 5, 2025

• AgentSafety

  Public
  77 forks•186186 stars•22 issues•00 pull requests•Updated Oct 31, 2025Oct 31, 2025

• WebDreamer

  Public
  [TMLR'25] "Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents"

  Python

  •66 forks•102102 stars•55 issues•00 pull requests•Updated Oct 5, 2025Oct 5, 2025

• HippoRAG

  Public
  [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external document…

  Python

  •

  MIT License

  •358358 forks•3.5k3.5k stars•1818 issues•44 pull requests•Updated Sep 4, 2025Sep 4, 2025

• AttributionBench

  Public
  [ACL'24 Findings] AttributionBench: How Hard is Automatic Attribution Evaluation?

  Python

  •22 forks•1010 stars•11 issue•00 pull requests•Updated Aug 18, 2025Aug 18, 2025

• hal-harness

  Public
  Python

  •5555 forks•00 stars•00 issues•00 pull requests•Updated Aug 18, 2025Aug 18, 2025

• AutoSDT

  Public
  [EMNLP'25] AutoSDT is a fully automatic pipeline to collect data-driven scientific coding tasks to train co-scientist models.

  bioinformaticsneurosciencecomputational-chemistry+ 4

  bioinformaticsneurosciencecomputational-chemistrypsychologygeographical-information-systemai4sciencescientific-code

  Python

  •

  MIT License

  •11 fork•1818 stars•11 issue•00 pull requests•Updated Aug 11, 2025Aug 11, 2025

• WebGuard

  Public
  WebGuard: Building a Generalizable Guardrail for Web Agents

  Python

  •

  MIT License

  •00 forks•1313 stars•44 issues•00 pull requests•Updated Jul 28, 2025Jul 28, 2025

• GrokkedTransformer

  Public
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'

  Python

  •

  MIT License

  •2626 forks•238238 stars•33 issues•00 pull requests•Updated Jul 19, 2025Jul 19, 2025